BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:Boulder NLP Seminar: Idan Blank
X-WR-TIMEZONE:Mountain Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260609T212547Z
UID:tag:localist.com\,2008:EventInstance_51834412102735
DTSTART:20260204T181500Z
DTEND:20260204T191500Z
DESCRIPTION:Title: Understanding “Understanding” In Large Language Mode
 ls\n \nAbstract:\nDo Large Language Models (LLMs) “understand” the lan
 guage that they process? In this talk\, I’ll describe three studies that
  adapt experimental approaches from human psycho- and neuro-linguistics to
  test whether LLMs exhibit signatures of human-like comprehension. First\,
  I will ask whether semantic information can “penetrate” and influence
  syntactic processing in LLMs—like it does in humans—or whether some s
 yntactic processing stages in LLMs are “encapsulated” from meaning. Se
 cond\, I will ask whether LLMs represent a fundamental aspect of linguisti
 c meaning: distinguishing between agents and patients in sentences. Third\
 , I will ask whether Large Vision-Language Models use visual context to in
 terpret language in a manner that exhibits pragmatic-like sensitivity to w
 hether expressions that refer to objects are felicitous\, under-informativ
 e\, or over-informative. These studies reveal both similarities and differ
 ences between LLMs and humans\, breaking comprehension into theoretically-
 informed constructs and promoting a nuanced view of how\, and in what sens
 e\, LLMs understand language.\n \nBio:\nIdan A. Blank is an Assistant Prof
 essor of Psychology and Linguistics at the University of California\, Los 
 Angeles. He leads the BlankLangLab\, which studies language comprehension 
 in biological and artificial minds\, examining how meaning is represented 
 and processed in the human brain and in AI systems. Using functional neuro
 imaging\, behavioral experiments\, and computational approaches\, his work
  investigates how various information sources are integrated during langua
 ge processing\, and how the “mental labor” of comprehension is divided
  between different cognitive systems. He received his PhD in Cognitive Sci
 ence from MIT\, followed by a post-doc at the McGovern Institute for Brain
  Research.
GEO:40.007888;-105.270477
LOCATION:Hellems Arts and Sciences\, N380
SUMMARY:Boulder NLP Seminar: Idan Blank
URL;VALUE=URI:https://calendar.colorado.edu/event/boulder-nlp-seminar-idan-
 blank
CATEGORIES:Colloquium/Seminar
END:VEVENT
END:VCALENDAR
